# coding=utf-8
# Copyright 2023 EleutherAI The HuggingFace Inc. team. and KDF.ai All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" GPTJiang model configuration"""

from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging


logger = logging.get_logger(__name__)

GPT_JIANG_PRETRAINED_CONFIG_ARCHIVE_MAP = {}


class GPTJiangConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`GPTJiangModel`]. It is used to instantiate an
    GPTJiang model according to the specified arguments, defining the model architecture. Instantiating a configuration
    with the defaults will yield a similar configuration to that of the GPTJiang

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.


    Args:
        vocab_size (`int`, *optional*, defaults to 50432):
            Vocabulary size of the GPTJiang model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`GPTJiangModel`].
        hidden_size (`int`, *optional*, defaults to 6144):
            Dimension of the encoder layers and the pooler layer.
        num_hidden_layers (`int`, *optional*, defaults to 44):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 64):
            Number of attention heads for each attention layer in the Transformer encoder.
        intermediate_size (`int`, *optional*, defaults to 24576):
            Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"selu"` and `"gelu_new"` are supported.
        rotary_pct (`float`, *optional*, defaults to 0.25):
            percentage of hidden dimensions to allocate to rotary embeddings
        rotary_emb_base (`int`, *optional*, defaults to 10000)
            base for computing rotary embeddings frequency
        max_position_embeddings (`int`, *optional*, defaults to 2048):
            The maximum sequence length that this model might ever be used with. Typically set this to something large
            just in case (e.g., 512 or 1024 or 2048).
        initializer_range (`float`, *optional*, defaults to 1e-5):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models). Only
            relevant if `config.is_decoder=True`.
        use_parallel_residual (`bool`, *optional*, defaults to `True`):
            Whether to use a "parallel" formulation in each Transformer layer, which can provide a slight training
            speedup at large scales (e.g. 20B).
        Example:

    ```python
    >>> from transformers import GPTJiangConfig, GPTJiangModel

    >>> # Initializing a GPTJiang style configuration
    >>> configuration = GPTJiangConfig()

    >>> # Initializing a model (with random weights) from the gpt-jiang style configuration
    >>> model = GPTJiangModel(configuration)  # doctest: +SKIP

    >>> # Accessing the model configuration
    >>> configuration = model.config  # doctest: +SKIP
    ```"""
    model_type = "gpt_jiang"

    def __init__(
        self,
        vocab_size=57000,
        hidden_size=5120,
        num_hidden_layers=48,
        num_attention_heads=40,
        intermediate_size=12288,
        hidden_act="gelu",
        rotary_pct=1.0,
        rotary_emb_base=10000,
        max_position_embeddings=4096,
        initializer_range=0.02,
        layer_norm_eps=1e-5,
        use_cache=True,
        bos_token_id=0,
        eos_token_id=2,
        tie_word_embeddings=False,
        use_parallel_residual=True,
        gated=True,
        mlp_bias=False,
        **kwargs,
    ):
        super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.intermediate_size = intermediate_size
        self.hidden_act = hidden_act
        self.rotary_pct = rotary_pct
        self.rotary_emb_base = rotary_emb_base
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.use_cache = use_cache
        self.tie_word_embeddings = tie_word_embeddings
        self.use_parallel_residual = use_parallel_residual
        self.gated = gated
        self.mlp_bias = mlp_bias